Lifeboat Foundation: Safeguarding Humanity
Toggle light / dark theme

Blog

Category: genetics

AI to predict the risk of cancer metastases

Metastasis remains the leading cause of death in most cancers, particularly colon, breast and lung cancer. Currently, the first detectable sign of the metastatic process is the presence of circulating tumor cells in the blood or in the lymphatic system. By then, it is already too late to prevent their spread. Furthermore, while the mutations that lead to the formation of the original tumors are well understood, no single genetic alteration can explain why, in general, some cells migrate and others do not.

“The difficulty lies in being able to determine the complete molecular identity of a cell – an analysis that destroys it – while observing its function, which requires it to remain alive,” explains the senior author. “To this end, we isolated, cloned and cultured tumor cells,” adds a co-first author of the study. “These clones were then evaluated in vitro and in a mouse model to observe their ability to migrate through a real biological filter and generate metastases.”

The analysis of the expression of several hundred genes, carried out on about thirty clones from two primary colon tumors, identified gene expression gradients closely linked to their migratory potential. In this context, accurate assessment of metastatic potential does not depend on the profile of a single cell, but on the sum of interactions between related cancer cells that form a group.

The gene expression signatures obtained were integrated into an artificial intelligence model developed by the team. “The great novelty of our tool, called ‘Mangrove Gene Signatures (MangroveGS)’, is that it exploits dozens, even hundreds, of gene signatures. This makes it particularly resistant to individual variations,” explains another co-first author of the study. After training, the model achieved an accuracy of nearly 80% in predicting the occurrence of metastases and recurrence of colon cancer, a result far superior to existing tools. In addition, signatures derived from colon cancer can also predict the metastatic potential of other cancers, such as stomach, lung and breast cancer.

After training, the model achieved an accuracy of nearly 80% in predicting the occurrence of metastases and recurrence of colon cancer, a result far superior to existing tools. In addition, signatures derived from colon cancer can also predict the metastatic potential of other cancers, such as stomach, lung and breast cancer.

Thanks to MangroveGS, tumor samples are sufficient: cells can be analysed and their RNA sequenced at the hospital, then the metastatic risk score quickly transmitted to oncologists and patients via an encrypted Mangrove portal that has analysed the anonymised data.

“This information will prevent the overtreatment of low-risk patients, thereby limiting side effects and unnecessary costs, while intensifying the monitoring and treatment of those at high risk,” adds the senior author. “It also offers the possibility of optimising the selection of participants in clinical trials, reducing the number of volunteers required, increasing the statistical power of studies, and providing therapeutic benefits to the patients who need it most.” ScienceMission sciencenewshighlights.

Continue reading “AI to predict the risk of cancer metastases” | >

DNA-Protein Crosslinks Explain Accelerated Aging in Progeria

In Ruijs-Aalfs progeria syndrome, patients experience accelerated aging and liver cancer.

Now, scientists showed that mutations in a certain gene prevent cells from repairing DNA damage during mitosis, triggering inflammatory immune responses that may fuel premature aging.

Read more.

Researchers have shown that harmful bonds between protein and DNA fuel immune attack in progeria. Pumping up a protein that cuts these bonds could prevent symptoms.

Procrastination in adulthood linked to brain development during adolescence

Procrastination, the tendency to unnecessarily delay or put off tasks even if this will have negative consequences, is a common behavior for many people. While occasionally delaying or putting off bothersome tasks is not necessarily problematic, severe and prolonged procrastination is closely tied to some neuropsychiatric disorders, including attention-deficit/hyperactivity disorder (ADHD) and anxiety disorders.

Unveiling patterns in the brain’s structure and genetic factors linked to procrastination could help to reliably uncover this tendency to postpone tasks in affected individuals. This could in turn inform the development of preventative strategies or interventions that tackle procrastination early, before it exacerbates other underlying mental health disorders.

Researchers at the Chinese Academy of Sciences and other institutes in China recently carried out a study aimed at shedding new light on the biological and genetic roots of procrastination. Their paper, published in Molecular Psychiatry, outlines specific patterns in the brain’s structure during adolescence that are linked to procrastination in adulthood.

Different Autism Mutations Can Lead to Similar Brain Changes

The shared pathways were linked to neuron maturation, synapse formation, and the control of gene activity. Further analysis pointed to a group of genes involved in organizing DNA and regulating which genes are switched on or off. These genes sit high in the regulatory chain, influencing many downstream processes previously linked to autism.

To test whether this network played an active role, the team reduced the activity of several key regulators using CRISPR-based methods in neural cells. This led to downstream changes similar to those seen in the autism models.

However, organoids from individuals with idiopathic autism showed less consistent changes, likely reflecting the complex and distributed genetic risk seen in most autism cases.

CLN3 mediates chloride efflux from lysosomes

Lysosomes degrade damaged organelles and macromolecules to recycle nutrient components. Lysosomal storage diseases (LSDs) are linked to mutations of genes encoding lysosomal proteins and may lead to age-related disorders, including neurodegenerative diseases. But, how lysosomal dysfunction contributes to neurodegenerative diseases is not clear yet…

The researchers identify CLN3 (ceroid lipofuscinosis, neuronal 3), linked to Batten disease as a conserved lysosomal protein that regulates lysosomal chloride homeostasis, pH, and protein degradation.

Curcumin analog C1 is a natural compound with anti-inflammatory properties could enhance CLN3 activity and improve lysosomal function by activating TFEB. sciencenewshighlights ScienceMission https://sciencemission.com/CLN3-n-chloride-efflux-n-lysosomes

Wang et al. identify CLN3 as a conserved lysosomal protein that regulates lysosomal chloride homeostasis, pH, and protein degradation. Transcription factor EB (TFEB) activation enhances CLN3 function, revealing the TFEB-CLN3 signaling axis as a promising therapeutic target for lysosomal storage disorders.

Advancing regulatory variant effect prediction with AlphaGenome

What makes it special is its versatility. Where older models might only predict how a mutation affects gene activity, AlphaGenome forecasts thousands of biological outcomes simultaneously—whether a variant will alter how DNA folds, change how proteins dock onto genes, disrupt the splicing machinery that edits genetic messages, or modify histone “spools” that package DNA. It’s essentially a universal translator for genetic regulatory language.

AlphaGenome is a deep learning model designed to learn the sequence basis of diverse molecular phenotypes from human and mouse DNA (Fig. 1a). It simultaneously predicts 5,930 human or 1,128 mouse genome tracks across 11 modalities covering gene expression (RNA-seq, CAGE and PRO-cap), detailed splicing patterns (splice sites, splice site usage and splice junctions), chromatin state (DNase, ATAC-seq, histone modifications and transcription factor binding) and chromatin contact maps. These span a variety of biological contexts, such as different tissue types, cell types and cell lines (see Supplementary Table 1 for the summary and Supplementary Table 2 for the complete metadata). These predictions are made on the basis of 1-Mb of DNA sequence, a context length designed to encompass a substantial portion of the relevant distal regulatory landscape. For instance, 99% (465 of 471) of validated enhancer–gene pairs fall within 1 Mb (ref. 12).

AlphaGenome uses a U-Net-inspired2,13 backbone architecture (Fig. 1a and Extended Data Fig. 1a) to efficiently process input sequences into two types of sequence representations: one-dimensional embeddings (at 1-bp and 128-bp resolutions), which correspond to representations of the linear genome, and two-dimensional embeddings (2,048-bp resolution), which correspond to representations of spatial interactions between genomic segments. The one-dimensional embeddings serve as the basis for genomic track predictions, whereas the two-dimensional embeddings are the basis for predicting pairwise interactions (contact maps). Within the architecture, convolutional layers model local sequence patterns necessary for fine-grained predictions, whereas transformer blocks model coarser but longer-range dependencies in the sequence, such as enhancer–promoter interactions.

Deep-learning algorithms enhance mutation detection in cancer and RNA sequencing

Researchers from the Faculty of Engineering at The University of Hong Kong (HKU) have developed two innovative deep-learning algorithms, ClairS-TO and Clair3-RNA, that significantly advance genetic mutation detection in cancer diagnostics and RNA-based genomic studies.

The pioneering research team, led by Professor Ruibang Luo from the School of Computing and Data Science, Faculty of Engineering, has unveiled two groundbreaking deep-learning algorithms—ClairS-TO and Clair3-RNA—set to revolutionize genetic analysis in both clinical and research settings.

Leveraging long-read sequencing technologies, these tools significantly improve the accuracy of detecting genetic mutations in complex samples, opening new horizons for precision medicine and genomic discovery. Both research articles have been published in Nature Communications.

/* */